Method and apparatus for mapping prefixes and values of a hierarchical space to other representations
Methods and apparatus are disclosed for mapping prefixes and/or values of a hierarchical space to other representations while maintaining the original hierarchy, which may be especially useful in conjunction with associative memories, such as binary and ternary content-addressable memories. In one implementation, a set of prefixes associated with a hierarchical space is received. A new representation of the set of prefixes is developed, such as by using a trie representation, with the new representation maintaining the original hierarchical relationship. This new representation may be an optimized representation selected to reduce or minimize the depth of the trie or some other cost. A set of new prefixes are generated along with a set of lookup values. During processing, a value, such as that included in a packet, is converted to one of the lookup values, which is used to generate a lookup word for use in matching against the new prefixes.
Latest Cisco Technology, Inc. Patents:
This invention especially relates to mapping prefixes and values of a hierarchical space to other representations; and more particularly, the invention relates to mapping prefixes and values of a hierarchical space to another representations using a trie representation.
BACKGROUND OF THE INVENTIONThe communications industry is rapidly changing to adjust to emerging technologies and ever increasing customer demand. This customer demand for new applications and increased performance of existing applications is driving communications network and system providers to employ networks and systems having greater speed and capacity (e.g., greater bandwidth). In trying to achieve these goals, a common approach taken by many communications providers is to use packet switching technology. Increasingly, public and private communications networks are being built and expanded using various packet technologies, such as Internet Protocol (IP).
A network device, such as a switch or router, typically receives, processes, and forwards or discards a packet based on one or more criteria, including the type of protocol used by the packet, addresses of the packet (e.g., source, destination, group), and type or quality of service requested. Additionally, one or more security operations are typically performed on each packet. But before these operations can be performed, a packet classification operation must typically be performed on the packet.
Packet classification as required for access control lists (ACLs) and forwarding decisions is a demanding part of switch and router design. This packet classification of a received packet is increasingly becoming more difficult due to ever increasing packet rates and number of packet classifications. For example, ACLs require matching packets on a subset of fields of the packet flow label, with the semantics of a sequential search through the ACL rules. IP forwarding requires a longest prefix match.
One known approach uses binary and/or ternary content-addressable memories to perform packet classification. Ternary content-addressable memories allow the use of wildcards in performing their matching, and thus are more flexible than binary content-addressable memories. These content-addressable memories are expensive in terms of power consumption and space, and are limited in the size of an input word (e.g., 72, 144, 288 bits, etc.) on which a lookup operation is performed as well as the number of entries which can be matched.
Various applications that use packet classification, such as Security Access Control, Quality of Service etc., typically need to match source and/or destination addresses. These addresses can be quite large, and possibly too large for providing all bits representing one or more addresses to a content-addressable memory. For example, Internet Protocol version 6 (IPv6) uses addresses having a length of 128 bits and a typical large content-addressable memory has a maximum search width of 288 bits. Therefore, almost all the bits of a content-addressable memory would be used for matching the source and destination addresses, while providing a small, and quite possibly insufficient number of input bits for matching other criteria such as source and destination port numbers, protocol and other header fields, etc. Needed are new methods and apparatus for performing lookup operations, especially for IPv6 and other addresses, using content-addressable memories and other devices.
SUMMARY OF THE INVENTIONSystems and methods are disclosed for mapping prefixes and/or values of a hierarchical space to other representations. In one embodiment, a first representation of a hierarchical relationship among a multiple first prefixes is generated. An optimized representation of the hierarchical relationship among the multiple first prefixed is determined. A mapping of the plurality of first prefixes into a plurality of second prefixes is generated based on the optimized representation.
The appended claims set forth the features of the invention with particularity. The invention, together with its advantages, may be best understood from the following detailed description taken in conjunction with the accompanying drawings of which:
Methods and apparatus are disclosed for mapping prefixes and/or values of a hierarchical space to other representations while maintaining the original hierarchy, which may be especially useful in conjunction with associative memories, such as, but not limited to binary and ternary content-addressable memories (CAMs). Embodiments described herein include various elements and limitations, with no one element or limitation contemplated as being a critical element or limitation. Each of the claims individually recite an aspect of the invention in its entirety. Moreover, some embodiments described may include, but are not limited to, inter alia, systems, networks, integrated circuit chips, embedded processors, ASICs, methods, and computer-readable medium containing instructions. The embodiments described hereinafter embody various aspects and configurations within the scope and spirit of the invention, with the figures illustrating exemplary and non-limiting configurations.
As used herein, the term “packet” refers to packets of all types, including, but not limited to, fixed length cells and variable length packets, each of which may or may not be divisible into smaller packets or cells. Moreover, these packets may contain one or more types of information, including, but not limited to, voice, data, video, and audio information. Furthermore, the term “system” is used generically herein to describe any number of components, elements, sub-systems, devices, packet switch elements, packet switches, routers, networks, computer and/or communication devices or mechanisms, or combinations of components thereof. The term “computer” is used generically herein to describe any number of computers, including, but not limited to personal computers, embedded processors and systems, control logic, ASICs, chips, workstations, mainframes, etc. The term “device” is used generically herein to describe any type of mechanism, including a computer or system or component thereof. The terms “task” and “process” are used generically herein to describe any type of running program, including, but not limited to a computer process, task, thread, executing application, operating system, user process, device driver, native code, machine or other language, etc., and can be interactive and/or non-interactive, executing locally and/or remotely, executing in foreground and/or background, executing in the user and/or operating system address spaces, a routine of a library and/or standalone application, and is not limited to any particular memory partitioning technique. The steps and processing of signals and information illustrated in the figures are typically be performed in a different serial or parallel ordering and/or by different components in various embodiments in keeping within the scope and spirit of the invention. Moreover, the terms “network” and “communications mechanism” are used generically herein to describe one or more networks, communications mediums or communications systems, including, but not limited to the Internet, private or public telephone, cellular, wireless, satellite, cable, local area, metropolitan area and/or wide area networks, a cable, electrical connection, bus, etc., and internal communications mechanisms such as message passing, interprocess communications, shared memory, etc. The terms “first,” “second,” etc. are typically used herein to denote different units (e.g., a first element, a second element). The use of these terms herein does not necessarily connote an ordering such as one unit or event occurring or coming before the another, but rather provides a mechanism to distinguish between particular units. Additionally, the extensible disclosure herein may refer a data structure, component, system, element, etc. in the singular tense, the disclosure is extensible and such discussion implies zero, one, or more than one of the particular item; and the converse is also true. Moreover, the phrase “based on x” is used to indicate a minimum set of items x from which something is derived, wherein “x” is extensible and does not necessarily describe a complete list of items on which the operation is based. Additionally, the phrase “coupled to” is used to indicate some level of direct or indirect connection between two elements or devices, with the coupling device or devices modify or not modifying the coupled signal or communicated information. Moreover, the term “or” is used herein to identify an alternative selection of one or more, including all, of the conjunctive items.
In one view, a trie is a directed path through a tree with each path through the tree qualified by a unique result. Each child of a trie is associated with a symbol from a finite alphabet depending on its relation to its parent node. A binary trie is a directed path through a binary tree with each path through the tree qualified by a unique result. This unique result is typically codified by the path taken with a one or zero representing a left or right path taken to reach the desired node. A prefix is typically a string of characters that appears at the beginning of a longer string of characters or it may be a string in and of itself. In many cases of practical interest the characters in a prefix are binary digits (i.e., ones and zeroes). A prefix is sometimes terminated by a wildcard, such as an asterisk, which represents the remaining arbitrary binary digits in a longer, fixed-length or arbitrary length string.
Methods and apparatus are disclosed for mapping prefixes and/or values of a hierarchical space to other representations while maintaining the original hierarchy, which may be especially useful in conjunction with associative memories, such as, but not limited to binary and ternary content-addressable memories. Typically, in the original space, a longest matching operation is performed using a value on a set of prefixes. It is typically important that the same results occur in a mapped spaced. Thus, in one embodiment, the new mapped space must maintain certain attributes of the original space, such as the same hierarchical structure and longest matching attributes.
In one embodiment, a set of prefixes associated with a hierarchical space is received. A new representation of the set of prefixes is developed, such as by using a trie representation, with the new representation maintaining the original hierarchical relationship. This new representation may be an optimized representation selected to reduce or minimize the depth of the trie or some other cost. A set of new prefixes are generated along with a set of lookup values. During processing, a value, such as that included in a packet, is converted to one of the lookup values, which is used to generate a lookup word for use in matching against the new prefixes. A new representation may be generated for each of multiple spaces for any parameter or parameters which will be used in a lookup operation and for any processing function. For example, in a communications device such as a router, these spaces include, but are not to limited network addresses (e.g., source, destination, etc.), port numbers, quality of service parameters, and policing values. These packet processing functions include, but are not limited to destination, policy-based, priority and other types of routing, netflow operations, netflow statistic, quality of service, and policing functions. Of course, the spaces and functions used are dependent on the particular application of one embodiment.
In one embodiment, programming engine 100 includes a processor 102, memory 101, storage devices 104, and programming interface 105, which are electrically coupled via one or more communications mechanisms 109 (shown as a bus for illustrative purposes). Various embodiments of programming engine 100 may include more or less elements. The operation of programming engine 100 is typically controlled by processor 102 using memory 101 and storage devices 104 to perform one or more tasks or processes. Memory 101 is one type of computer-readable medium, and typically comprises random access memory (RAM), read only memory (ROM), flash memory, integrated circuits, and/or other memory components. Memory 101 typically stores computer-executable instructions to be executed by processor 102 and/or data which is manipulated by processor 102 for implementing functionality in accordance with the invention. Storage devices 104 are another type of computer-readable medium, and typically comprise solid state storage media, disk drives, diskettes, networked services, tape drives, and other storage devices. Storage devices 104 typically store computer-executable instructions to be executed by processor 102 and/or data which is manipulated by processor 102 for implementing functionality in accordance with the invention.
After the one or more lookup values 273 are generated, a lookup operation is typically performed by associative memory 260 to produce result 261, which is typically used as input to a memory (e.g., SRAM) 262 to produce a result 265 for use by packet processor 220. In one embodiment, result 261 is returned to packet processor 220 in processing one or more of the received packets 240. In one embodiment, lookup word 255 includes multiple mapped lookup values 273, while in one embodiment, lookup word 255 includes a single mapped lookup value 273. In one embodiment, a single associative memory includes entries used in converting original lookup values 279 to mapped lookup values 273 and entries used in performing a lookup operation on lookup words 255.
When all address spaces have been processed as determined in process block 402, then, as determined in process block 420, if a match is to be performed using lookup values and prefixes from multiple spaces, then in process blocks 422 and 424, the matching entries are generated based on the prefix values of previously generated new hierarchical representations, and one or more associative memories and/or data structures are programmed with these generated entries. Processing is complete as indicated by process block 426.
Note, this processing is described in terms of receiving and processing packets. However, the invention is extensible, and not limited to processing packets. Rather, the invention may be used for processing any type of information.
Processing begins with process block 440, and proceeds to process block 442, wherein a packet is received. Next, in process block 444, information (e.g., source address, destination address, port fields, service type, or other packet header or data fields) is extracted on which to perform a lookup and matching operations. Next, as determined in process block 446, while there are more spaces associated with the extracted information, convert the original values of a particular space to lookup values by typically finding the longest matching prefix in the prefix mapping data structure in process block 448. Next, in process block 450, one or more lookup words are generated including one or more lookup values previously generated. In one embodiment, multiple lookup words include a same lookup value (e.g., a source or destination address), in which case, an original value need only be converted to its corresponding lookup value once. Next, in process block 452, one or more associative memory, database, or other lookup operations are performed using the one or more generated lookup words. In process block 454, a packet is processed or other operation performed based on the results of the lookup operation. Processing returns to process block 442 to receive and process more packets.
Turning first to
Next in process block 510 of
Next, in process block 514, an optimized trie representation is generated for the modified ancestor tree. For example, the cost is defined in one embodiment as the number of bits required to represent a value or address, which is equivalent in one embodiment to the depth of the mapped trie representation.
For example, illustrated in
Processing of the flow diagram illustrated in
In view of the many possible embodiments to which the principles of our invention may be applied, it will be appreciated that the embodiments and aspects thereof described herein with respect to the drawings/figures are only illustrative and should not be taken as limiting the scope of the invention. For example and as would be apparent to one skilled in the art, many of the process block operations can be re-ordered to be performed before, after, or substantially concurrent with other operations. Also, many different forms of data structures could be used in various embodiments. The invention as described herein contemplates all such embodiments as may come within the scope of the following claims and equivalents thereof.
Claims
1. A method comprising:
- determining a binary trie representation for a plurality of prefixes;
- determining an ancestor tree based on the binary trie representation;
- determining an optimized trie representation of the ancestor tree; and
- determining a mapping of the plurality of the prefixes into a plurality of second prefixes based on the optimized trie representation.
2. The method of claim 1, further comprising extracting the plurality of prefixes from a configuration table.
3. The method of claim 1, wherein the configuration table contains access control, quality of service, or routing information.
4. The method of claim 1, further causing an associative memory to be programmed with the plurality of second prefixes.
5. The method of claim 4, wherein the associative memory is a content-addressable memory.
6. The method of claim 1, further comprising determining a set of mapped lookup values based on the optimized representation.
7. The method of claim 6, further comprising causing the plurality of mapped lookup values to be stored in an associative memory.
8. A method comprising:
- generating a first representation of a hierarchical relationship among a plurality of first prefixes, which includes determining an ancestor tree based on the plurality of first prefixes;
- determining an optimized representation of the hierarchical relationship among the plurality of first prefixes, which includes determining an optimized trie representation of the ancestor tree; and
- generating a mapping of the plurality of first prefixes into a plurality of second prefixes based on the optimized representation.
9. The method of claim 8, wherein the first representation includes a trie.
10. The method of claim 9, wherein optimized representation includes a trie.
11. The method of claim 8, further comprising causing an associative memory to be programmed with the plurality of second prefixes.
12. The method of claim 11, wherein the associative memory includes a binary or ternary content-addressable memory.
13. The method of claim 8, further comprising storing the plurality of second prefixes in a data structure.
14. The method of claim 8, further comprising maintaining a data structure indicating the mapping.
15. The method of claim 8, wherein the plurality of first prefixes include a network address.
16. The method of claim 8, including adding a dummy node for each internal node of the first representation.
17. The method of claim 8, wherein the plurality of second prefixes includes a match all prefix.
18. The method of claim 8, wherein the plurality of second prefixes includes a dummy node for an internal node of the first representation.
19. The method of claim 8, further comprising determining a set of mapped lookup values based on the optimized representation.
20. The method of claim 19, further comprising causing the plurality of mapped lookup values to be stored in an associative memory.
21. A method of claim 8, further comprising:
- receiving a set of information including a first value;
- generating a lookup value from the set of mapped lookup values based on first value; and
- generating a lookup word based the lookup value.
22. The method of claim 21, further comprising:
- causing an associative memory to be programmed with the plurality of second prefixes; and
- initiating a lookup operation on the associative memory using the lookup word.
23. An apparatus comprising:
- means for determining a binary trie representation for a plurality of prefixes;
- means for determining an ancestor tree based on the binary trie representation;
- means for determining an optimized trie representation of the ancestor tree; and
- means for determining a mapping of the plurality of the prefixes into a plurality of second prefixes based on the optimized trie representation.
24. The apparatus of claim 23, further comprising means for programming an associative memory with the plurality of second prefixes.
25. An apparatus comprising:
- a programming engine for determining a mapping between a plurality of first prefixes having a hierarchical relationship and a plurality of second prefixes having the hierarchical relationship;
- a storage mechanism configured to maintain an indication of the mapping;
- translation logic to determine a particular one of the plurality of second prefixes based on a particular one of the plurality of first prefixes; and
- an associative memory to perform a lookup operation using the particular one of the plurality of second prefixes to generate a result;
- wherein the programming engine includes an optimizer for determining an ancestor tree based on the plurality of first prefixes; wherein the programming engine references the ancestor tree when determining the mapping.
26. The apparatus of claim 25, wherein the programming engine includes an associative memory programmer to program the associative memory.
27. The apparatus of claim 25, wherein the plurality of first prefixes correspond to a plurality of network addresses.
28. The apparatus of claim 25, wherein the plurality of prefixes are derived from an access control list.
29. The apparatus of claim 25, wherein the associative memory is a content-addressable memory.
30. The apparatus of claim 25, wherein the programming engine is further configured to determine a set of lookup values based on the set of first prefixes.
31. The apparatus of claim 30, further comprising a second associative memory for storing the set of lookup values.
32. An apparatus comprising:
- means for generating a first representation of a hierarchical relationship among a plurality of first prefixes, which includes means for determining an ancestor tree based on the plurality of first prefixes;
- means for determining an optimized representation of the hierarchical relationship among the plurality of first prefixes, which includes determining an optimized trie representation of the ancestor tree; and
- means for generating a mapping of the plurality of first prefixes into a plurality of second prefixes based on the optimized representation.
33. The apparatus of claim 32, wherein the first representation includes a trie.
34. The apparatus of claim 32, wherein optimized representation includes a trie.
35. The apparatus of claim 32, further comprising means for programming an associative memory with the plurality of second prefixes.
36. The apparatus of claim 32, further comprising means for determining a set of mapped lookup values based on the optimized representation.
37. The apparatus of claim 36, further comprising means for generating a lookup value from the set of mapped lookup values based on a particular value.
38. One or more computer-readable media containing computer-executable instructions for performing operations, said operations comprising:
- determining a binary trie representation for a plurality of prefixes;
- determining an ancestor tree based on the binary trie representation;
- determining an optimized trie representation of the ancestor tree; and
- determining a mapping of the plurality of the prefixes into a plurality of second prefixes based on the optimized trie representation.
39. The computer-readable media of claim 38, wherein said operations comprise extracting the plurality of prefixes from a configuration table.
40. The computer-readable media of claim 38, wherein the configuration table contains access control, quality of service, or routing information.
41. The computer-readable media of claim 38, wherein said operations comprise causing an associative memory to be programmed with the plurality of second prefixes.
42. The computer-readable media of claim 41, wherein the associative memory is a content-addressable memory.
43. The computer-readable media of claim 38, wherein said operations comprise determining a set of mapped lookup values based on the optimized representation.
44. The method of claim 43, wherein said operations comprise causing the plurality of mapped lookup values to be stored in an associative memory.
45. One or more computer-readable media containing computer-executable instructions for performing operations, said operations comprising:
- generating a first representation of a hierarchical relationship among a plurality of first prefixes, which includes determining an ancestor tree based on the plurality of first prefixes;
- determining an optimized representation of the hierarchical relationship among the plurality of first prefixes, which includes determining an optimized the representation of the ancestor tree; and
- generating a mapping of the plurality of first prefixes into a plurality of second prefixes based on the optimized representation.
46. The computer-readable media of claim 45, wherein said operations comprise causing an associative memory to be programmed with the plurality of second prefixes.
47. The computer-readable media of claim 46, wherein said operations comprise storing the plurality of second prefixes in a data structure.
48. The computer-readable media of claim 45, wherein said operations include adding a dummy node for each internal node of the first representation.
49. The computer-readable media of claim 45, wherein the plurality of second prefixes includes a dummy node for an internal node of the first representation.
50. The computer-readable media of claim 45, wherein said operations comprise determining a set of mapped lookup values based on the optimized representation.
51. The computer-readable media of claim 50, wherein said operations comprise causing the plurality of mapped lookup values to be stored in an associative memory.
52. The computer-readable media of claim 45, wherein said operations comprise:
- receiving a set of information including a first value;
- generating a lookup value from the set of mapped lookup values based on first value; and
- generating a lookup word based the lookup value.
53. The computer-readable media of claim 52, wherein said operations comprise:
- causing an associative memory to be programmed with the plurality of second prefixes; and
- initiating a lookup operation on the associative memory using the lookup word.
5088032 | February 11, 1992 | Bosack |
5319763 | June 7, 1994 | Ho et al. |
5481540 | January 2, 1996 | Huang |
5515370 | May 7, 1996 | Rau |
5528701 | June 18, 1996 | Aref |
5651099 | July 22, 1997 | Konsella |
5721889 | February 24, 1998 | Miller et al. |
5740171 | April 14, 1998 | Mazzola et al. |
5781772 | July 14, 1998 | Wilkinson, III et al. |
5809501 | September 15, 1998 | Noven |
5829004 | October 27, 1998 | Au |
5842040 | November 24, 1998 | Hughes et al. |
5848416 | December 8, 1998 | Tikkanen |
5884297 | March 16, 1999 | Noven |
5898689 | April 27, 1999 | Kumar et al. |
5920886 | July 6, 1999 | Feldmeier |
5930359 | July 27, 1999 | Kempke et al. |
5956336 | September 21, 1999 | Loschke et al. |
6000008 | December 7, 1999 | Simcoe |
6018524 | January 25, 2000 | Turner et al. |
6052683 | April 18, 2000 | Irwin |
6061368 | May 9, 2000 | Hitzelberger |
6067574 | May 23, 2000 | Tzeng |
6081440 | June 27, 2000 | Washburn et al. |
6091725 | July 18, 2000 | Cheriton et al. |
6097724 | August 1, 2000 | Kartalopoulos |
6115716 | September 5, 2000 | Tikkanen et al. |
6141738 | October 31, 2000 | Munter et al. |
6148364 | November 14, 2000 | Srinivasan et al. |
6181698 | January 30, 2001 | Hariguchi |
6236658 | May 22, 2001 | Essbaum et al. |
6237061 | May 22, 2001 | Srinivasan et al. |
6243667 | June 5, 2001 | Kerr et al. |
6289414 | September 11, 2001 | Feldmeier et al. |
6295576 | September 25, 2001 | Ogura et al. |
6298339 | October 2, 2001 | Bjornson |
6307855 | October 23, 2001 | Hariguchi |
6529909 | March 4, 2003 | Bowman-Amuah |
6717646 | April 6, 2004 | Park et al. |
6717946 | April 6, 2004 | Hariguchi et al. |
6775737 | August 10, 2004 | Warkhede et al. |
20030174717 | September 18, 2003 | Zabarski et al. |
WO 01/052063 | July 2001 | WO |
- Stefan Nilsson and Gunnar Karlsson, “IP-Address Lookup Using LC-Tries,” IEEE Journal on Selected Areas in Communications, Jun. 1999 (12 pages).
- Fast IP routing with LC-Tries; achieving gbit/see speed in software, (Internet/Web/Online Service Information); Stefan Nilsson et al.; Dr. Dobb's Journal; Aug. 1998; vol. 23, No. 8, p. 70 (5).
- Donald R. Morrison, “Patricia—Practical Algorithm to Retrieve Information Coded in Alphanumeric,” Journal of the ACM, vol. 15, No. 4, Oct. 1968, pp. 514-534.
- Waldvogel et al., “Scalable High Speed IP Routing Lookups,” Proc. SIGCOMM '97, ACM, 1997, pp. 25-36.
- Lampson et al., “IP Lookups Using Multiway and Multicolumn Search,” Proc. Infocom 98, Mar. 1998, 24 pages.
- V. Srinivasan and George Varghese, “Faster IP Lookups using Controlled Prefix Expansion,” ACM SIGMETRICS Performance Evaluation Review, vol. 26 No. 1, Jun. 1998, p. 1-10.
- Stefan Nilsson and Gunnar Karlsson, “Fast Address Look-up for Internet Routers,” Proceedings of IEEE Broadband Communications, Apr. 1998, 12 pages.
- William N. Eatherton, Hardware-Based Internet Protocol Prefix Lookups, Master's thesis, Sever Institute, Washington University, St. Louis, MO, May 1999, 109 pages.
- Lampson et al., “IP Lookups Using Multiway and Multicolumn Search,” IEEE Transactions on Networking, vol. 7, No. 3, Jun. 1999, pp. 324-334.
- Lockwood et al., “Field Programmable Port Extender (FPX) for Distributed Routing and Queuing,” Proceedings of the ACM/SIGDA international symposium on Field programmable gate arrays, Feb. 2000, pp. 137-144.
- Ruiz-Sanchez et al., “Survey and Taxonomy of IP Address Lookup Algorithms,” IEEE Network Magazine, vol. 15, No. 2, Mar./Apr. 2001, pp. 8-23.
- Pankaj Gupta and Nick McKewon, “Algorithms for Packet Classification,” IEEE Network Magazine, vol. 15, No. 2, Mar./Apr. 2001, pp. 24-32.
- Iyer et al., “ClassiPI: An Architecture for Fast and Flexible Packet Classification,” IEEE Network Magazine, vol. 15, No. 2, Mar./Apr. 2001, pp. 33-41.
- Waldvogel et al., “Scalable High Speed Prefix Matching,” ACM Transactions on Computer Systems, vol. 19, No. 4, Nov. 2001, pp. 440-482.
- Jon P. Wade and Charles G. Sodini, “A Ternary Content Addressable Search Engine,” IEEE Journal of Solid-State Circuits, vol. 24, No. 4, Aug. 1989, pp. 1003-1013.
- Teuvo Kohonen, Content-Addressable Memories, 1987, pp. 128-129 and 142-144, Springer-Verlang, New York.
- Brian Dipert, ed., “Special-purpose SRAMs Smooth the Ride,” EDN, Jun. 24, 1999, pp. 93-104.
- “Extending the LANCAM Comparand,” Application Brief AB-N3, Rev. 1.0a Draft, Music Semiconductors, Milpitas, CA, Sep. 30, 1998, 4 pages.
- “Advantages of CAM in ASIC-Based Network Address Processing,” Application Brief AB-N11, Rev. 1.2a Draft, Music Semiconductors, Milpitas, CA, Sep. 30, 1998, 4 pages.
- “Virtual Memory Applications of the MU9C1480A LANCAM,” Application Note AN-N3, Rev. 1a, Music Semiconductors, Milpitas, CA, Sep. 30, 1998, 12 pages.
- “Using the MU9C1965A LANCAM MP for Data Wider than 128 Bits,” Application Note AN-N19, Rev. 1a, Music Semiconductors, Milpitas, CA, Sep. 30, 1998, 16 pages.
- “Fast IPv4 and IPv4 CIDR Address Translation and Filtering Using the MUAC Routing CoProcessor (RCP),” Application Note AN-N25, Rev. 0a, Music Semiconductors, Milpitas, CA, Oct. 1, 1998, 16 pages.
- “Using MUSIC Devices and RCPs for IP Flow Recognition,” Application Note AN-N27, Rev. 0, Music Semiconductors, Milpitas, CA, Oct. 21, 1998, 20 pages.
- “Wide Ternary Searches Using Music CAMs and RCPs,” Application Note AN-N31, Rev. 0, Music Semiconductors, Milpitas, CA, Apr. 13, 1999, 8 pages.
Type: Grant
Filed: Jan 8, 2002
Date of Patent: Nov 29, 2005
Assignee: Cisco Technology, Inc. (San Jose, CA)
Inventors: Priyank Ramesh Warkhede (Santa Clara, CA), Stewart Frederick Bryant (Surrey)
Primary Examiner: Pierre-Michel Bataille
Attorney: The Law Office of Kirk D. Williams
Application Number: 10/042,847